Related papers: On-device Semantic Selection Made Low Latency and …

Generative Sequential Recommendation (GSR) has emerged as a promising paradigm, reframing recommendation as an autoregressive sequence generation task over discrete Semantic IDs (SIDs), typically derived via codebook-based quantization.…

Visual instruction tuning adapts pre-trained Multimodal Large Language Models (MLLMs) to follow human instructions for real-world applications. However, the rapid growth of these datasets introduces significant redundancy, leading to…

Modern online large language model (LLM) services, such as Retrieval-Augmented Generation (RAG) and agent systems, increasingly expose two prominent characteristics: prompt segmentation (e.g., system instructions, retrieved passages, tool…

Long-horizon language agents accumulate conversation history far faster than any fixed context window can hold, making memory management critical to both answer accuracy and serving cost. Existing approaches either expand the context window…

Long-range tasks demand reasoning over long inputs. However, existing solutions are limited, e.g., long-context models require large compute budgets, parameter-efficient fine-tuning (PEFT) needs training data, and retrieval-augmented…

Large Language Models (LLMs), constrained by their auto-regressive nature, suffer from slow decoding. Speculative decoding methods have emerged as a promising solution to accelerate LLM decoding, attracting attention from both systems and…

With the rapid progress of large language models (LLMs), financial information retrieval has become a critical industrial application. Extracting task-relevant information from lengthy financial filings is essential for both operational and…

Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora. However, small, high-quality subsets, known as coresets, can deliver comparable or superior…

Long-context LLM inference is bottlenecked not by compute but by the O(n) memory bandwidth cost of scanning the KV cache at every decode step -- a wall that no amount of arithmetic scaling can break. Recent photonic accelerators have…

Generative sequence modeling faces a fundamental tension between the expressivity of Transformers and the efficiency of linear sequence models. Existing efficient architectures are theoretically bounded by shallow, single-step linear…

Sparse tensors are the most used representation of sparse multidimensional data. Operations that decompose them, selecting their most important features while reducing their dimension, have become prevalent procedures in machine learning.…

We propose PRISM, a novel framework designed to overcome the limitations of 2D-based Preference-Based Reinforcement Learning (PBRL) by unifying 3D point cloud modeling and future-aware preference refinement. At its core, PRISM adopts a 3D…

We present PRISM, a comprehensive empirical study of mid-training design choices for large language models. Through controlled experiments across seven base models spanning four families (Granite, LLaMA, Mistral, Nemotron-H), two…

DEEPTHINK methods improve reasoning by generating, refining, and aggregating populations of candidate solutions, which enables strong performance on complex mathematical and scientific tasks. However, existing frameworks often lack reliable…

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

With the rapid emergence of personal AI agents based on Large Language Models (LLMs), implementing them on-device has become essential for privacy and responsiveness. To handle the inherently personal and context-dependent nature of…

To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to…

Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and resilient to the non-deterministic behavioral drift that characterizes production LLM…

Large reasoning models (LRMs) such as Claude 3.7 Sonnet and OpenAI o1 achieve strong performance on mathematical benchmarks using lengthy chain-of-thought (CoT) reasoning, but the resulting traces are often unnecessarily verbose. This…

Large Language Models (LLMs) present significant computational and memory challenges due to their extensive size, making pruning essential for their efficient deployment. Existing one-shot pruning methods often apply uniform sparsity…